from sklearn.preprocessing import MinMaxScaler, PolynomialFeatures
from sklearn.model_selection import train_test_split
# feature selection
from sklearn.feature_selection import RFE
if __name__ == '__main__':
# Set variables and path
save_figs = True
filename = snakemake.input[0]
# Print available access variables
# print(pyh22.load_car22.__doc__)
# Read in data -------------------------------------------------------------
data = pyh22.load_car22(filename, access_var="all", drop=True, version=1)
cytokines = Cytokines(data.cytokines).days_to_int()
# Plot missing data
#msno.matrix(cytokines.df)
# Get days relative to CRS
# crs_transform does not work on new dataset
days_to_index = data.cytokines_days_num.unstack().unstack(level=1)
days_to_index.index.rename(names='date', level=0, inplace=True)
# Merge with clinical data
days_outcome = pd.merge(data.secondary_outcome.reset_index(),
days_to_index.reset_index(),
on='patient_id')
from sklearn.feature_selection import RFE
if __name__ == '__main__':
# Set variables and path
save_figs = True
#filename_old = 'revisions/data/Full Cytokine_De-identified CD22 Data for Bioinformatics_3-30-20_v1.xlsx'
filename = 'revisions/data/clinical_data_05-12-20_v1.xlsx'
figs_path = 'datasets/CAR-T/new_data/' # choose path
# Print available access variables
print(pyh22.load_car22.__doc__)
# Read in data -------------------------------------------------------------
data = pyh22.load_car22(filename, access_var="all", drop=True, version=1)
cytokines = Cytokines(data.cytokines).days_to_int()
# Define features and target variable for baseline -------------------------
X = pd.concat(
[data.clinical,
cytokines.days_to_int().df[0],
data.pb_tbnk['0'],
data.bm_tbnk['0'],
data.inflammatory['0']],
axis=1,
sort=False)
y = data.outcome['HLH']
# Try building predictor for CRS+2 -----------------------------------------
